Computer Rating System Prediction Results for College Football (NCAA IA)

2016 Season Totals

Through 2016-09-25
Rank System Pct. Correct Against Spread Absolute Error Bias Mean Square Error games suw sul atsw atsl
1Atomic Football0.814430.5722212.3402-1.2784263.8061941583610377
2Line (updated)0.809280.5555612.1804-0.4021258.705194157376048
3Computer Adjusted Line0.809280.5565212.1881-0.4253258.562194157376451
4Liam Bressler0.809280.5380412.2128-0.4923259.018194157379985
5TeamRankings.com0.809280.5294112.5056-0.5757273.887194157379988
6Sagarin Golden Mean0.809280.5079412.6283-0.4031266.628194157379693
7System Median0.804120.4863412.5205-0.6557266.239194156388994
8System Average0.804120.4814812.5037-0.8084266.914194156389198
9Line (Midweek)0.8041212.2010-0.3093258.78019415638
10Catherwood Ratings0.803110.5434812.72020.4508273.3411931553810084
11Line (opening)0.798970.4695112.3376-0.4201262.390194155397787
12Ashby AccuRatings0.798970.5423712.4949-0.9793270.885194155399681
13Sagarin Recent0.798970.5185212.6032-0.4628265.603194155399891
14ThePowerRank.com0.798970.5585113.1272-1.6891296.1431941553910583
15Pigskin Index0.793810.5219812.59280.0053271.088194154409587
16Edward Kambour0.793810.4920612.8821-0.4609275.308194154409396
17DP Dwiggins0.788660.5245913.2938-1.8711306.142194153419687
18Sagarin Ratings0.788660.4973512.7874-0.4367269.687194153419495
19Dokter Entropy0.788660.5291012.4663-0.8579270.6441941534110089
20Stat Fox0.783510.5519112.36080.7116271.5051941524210182
21Moore Power Ratings0.783510.5502612.4306-0.8342270.0211941524210485
22ESPN FPI0.783510.5343912.6025-0.3958279.1111941524210188
23PI-Rate Bias0.783510.5343912.75200.1800275.9021941524210188
24Born Power Index0.783510.4867713.13120.2879289.396194152429297
25Brent Craig0.783510.4867713.1528-0.0390290.779194152429297
26Beck Elo0.778350.4521313.5853-1.0960300.1101941514385103
27CPA Rankings0.778350.5291013.4346-0.7896301.1781941514310089
28Massey Consensus0.778350.4973513.0640-0.3580283.758194151439495
29Donchess Inference0.778350.4946812.9180-0.9603282.474194151439395
30Sagarin Points0.778350.4920612.8309-0.4371271.315194151439396
31Payne Power Ratings0.773200.4391514.0060-1.0538323.8461941504483106
32Pi-Ratings Mean0.773200.4127013.4526-0.4886289.9611941504478111
33ARGH Power Ratings0.773200.5000013.4188-2.1997299.685194150449393
34NutShell Sports0.773200.4603213.2513-1.4199293.9191941504487102
35Pi-Rate Ratings0.773200.5291013.00630.4289284.6561941504410089
36Massey Ratings0.773200.5185212.8131-1.3121279.043194150449891
37Billingsley+0.768040.4497413.4019-0.8574302.6511941494585104
38CPA Retro0.768040.5026513.7888-0.9422311.269194149459594
39ComPughter Ratings0.762890.4973513.5102-0.0834293.642194148469495
40Dunkel Index0.762890.5238113.2514-0.0735298.067194148469990
41Keeper0.761660.5291013.7079-0.2785317.6041931474610089
42The Sports Cruncher0.757730.5483912.5545-0.4845281.0791941474710284
43Daniel Curry Index0.757730.5132313.4834-0.1184304.990194147479792
44FEI Projections0.757730.5245913.6495-0.7113301.936194147479687
45Howell0.757730.4917113.6829-2.0797317.493194147478992
46Marsee0.752580.4615414.64950.9381351.831194146488498
47Lee Burdorf0.752580.5079413.5031-0.8060308.850194146489693
48DirectorOfInformation0.752580.5079413.2860-0.1787296.426194146489693
49Super List0.747420.5053214.5467-0.0923353.964194145499593
50Laz Index0.747420.4444415.1156-1.9563359.3071941454984105
51Covers.com0.742270.4391515.0609-3.0507369.2491941445083106
52MDS Model0.736490.4895114.3427-0.0204395.376148109397073
53Stephen Kerns0.731960.5449714.2644-0.1994336.5131941425210386
54Billingsley0.731960.4444414.3201-2.2463346.4531941425284105
55Laffaye RWP0.726800.4521314.5820-3.5751366.3731941415385103
56Dave Congrove0.726800.5026514.0099-1.6249330.343194141539594
57PerformanZ Ratings0.721650.4709015.0847-2.8825375.9421941405489100
58Cleanup Hitter0.715030.4581014.8498-0.4455386.044193138558297
59Loudsound.org0.709840.4784917.1916-7.8341479.567193137568997
60PointShare0.627450.4705918.4745-0.4471531.0755132192427

* This system does not make predictions.  I make predictions for this
  system by translating it to a new scale that allows for making predictions.



Retrodictive records are found by taking the ratings from the current week
and applying them to the entire season to date.

The ideal system would be one that has the highest correct game decisions,
has the smallest mean error(deviation from the actual game result), and has
a bias of zero.

Mean Error = average[abs(prediction-actual)]

      Bias = agerage(prediction - actual)

      Std. = Standard Deviation of individual game biases